Machine learning for precision obstetrics: A comprehensive review of risk prediction models for hypertensive disorders and pregnancy-related syndromes.

Gestational diabetes mellitus (GDM), hypertensive disorders of pregnancy (HDP), preterm birth, and intrauterine growth restriction represent major contributors to maternal and neonatal morbidity worldwide. Traditional screening methods relying on single biomarkers or linear models often demonstrate limited predictive accuracy. This review examines the transformative role of machine learning (ML) in shifting obstetric care toward predictive, preventive, and personalized approaches. Advanced computational models integrating multimodal data sources clinical records, biochemical markers, multi-omics profiles, medical imaging, and lifestyle factors show promising performance. Ensemble methods such as Random Forest and XGBoost, alongside deep learning architectures, frequently outperform conventional logistic regression, achieving AUC values above 0.90 in selected cohorts. Emphasis is placed on preprocessing techniques for class imbalance (e.g., SMOTE), model interpretability via Explainable AI (SHAP), and privacy-preserving strategies like federated learning. While technical and ethical challenges including bias, external validation, and data heterogeneity remain, robust ML frameworks offer substantial potential for early risk stratification and timely intervention in precision obstetrics. Prospective, multicenter validation is essential for clinical translation.